构建基于机器学习方法的TKA后DVT形成的风险预测模型
Huanya Li1, Zhicheng He1, Pengcui Li2
1Academy of Medical Sciences, Shanxi Medical University, Shanxi, China.
Medicine
|December 30, 2025
概括
这项研究开发了一种物流模型,用于预测膝盖全关节整形术 (TKA) 后深静脉血栓形成 (DVT) 风险. 该模型确定了关键的风险因素,为TKA患者的DVT预防提供了有价值的工具.
科学领域:
- 整形外科手术 整形外科手术
- 心血管医学 心血管医学
- 在医疗保健中的数据科学.
背景情况:
- 深静脉血栓症 (DVT) 是膝关节全关节整形术 (TKA) 后的一种严重并发症.
- 准确的风险预测模型对于TKA后有效的DVT预防策略至关重要.
研究的目的:
- 构建和比较多个机器学习模型,用于预测TKA后DVT风险.
- 确定与TKA后DVT相关的关键风险因素.
- 确定临床应用的最佳预测模型.
主要方法:
- 对1238个TKA患者记录进行了回顾性分析.
- 使用拉索和博鲁塔来选择特征以确定风险因素.
- 开发并比较了六种机器学习模型:物流回归,XGBoost,随机森林,AdaBoost,梯度增强决策树和KNN.
- 使用决策曲线,校准曲线和ROC指标评估模型性能.
主要成果:
- 确定了11个危险因素,包括贫血,输血量,输血,高血压,D-二次体,血栓时间 (TT),CL,麻醉持续时间,手术持续时间,激活的部分血栓塑时间 (APTT) 和术后疼痛评分.
- 后勤回归模型展示了最佳的性能和概括能力.
- SHAP分析显示,较短的APTT,更长的麻醉时间,升高的TT,更高的疼痛分数,减少的D-二次数,减少的CL,增加的输血量,增加的血液损失,更短的手术时间和贫血与增加的DVT风险有关.
结论:
- 后勤模型是最佳的预测TKA后DVT风险.
- 识别和管理已识别的风险因素可以帮助减少TKA后的DVT发病率.
- 这种预测模型为临床医生在评估和预防DVT时提供了有价值的参考.
更多相关视频
相关概念视频
Venous Thrombosis III: Interprofessional Care
254
Venous thrombosis requires effective prevention and treatment strategies to improve patient outcomes and reduce potential complications.Prevention StrategiesHealthcare providers must prioritize preventing venous thromboembolism (VTE) for all adult patients upon admission. Interventions depend on bleeding and thrombosis risk, medical history, current medications, diagnoses, planned procedures, and patient preferences. Patients on bed rest should change positions every two hours and, if not...
254
Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
262
The key difference between Superficial Vein Thrombosis (SVT) and Deep Vein Thrombosis (DVT) lies in their location and severity.Clinical ManifestationsSVT typically presents with localized pain, tenderness, and redness along the course of a superficial vein, often accompanied by a palpable, cord-like structure under the skin. This condition is usually less dangerous than DVT but can be uncomfortable and may lead to complications such as cellulitis or, rarely, a clot extension into the deep...
262


